【tensorflow2.0】47.时间序列数据建模流程实例（总复习）

    本篇文章将利用TensorFlow2.0建立时间序列RNN模型，对国内的新冠肺炎疫情结束时间进行预测。数据集取自tushare。

import numpy as np
import pandas as pd 
import matplotlib.pyplot as plt
import tensorflow as tf 
from tensorflow.keras import models,layers,losses,metrics,callbacks 
#读取数据处理数据
%matplotlib inline
%config InlineBackend.figure_format = 'svg'

df = pd.read_csv("./data/covid-19.csv",sep = "\t")
df.plot(x = "date",y = ["confirmed_num","cured_num","dead_num"],figsize=(10,6))
plt.xticks(rotation=60)

dfdata = df.set_index("date")
dfdiff = dfdata.diff(periods=1).dropna()
dfdiff = dfdiff.reset_index("date")

dfdiff.plot(x = "date",y = ["confirmed_num","cured_num","dead_num"],figsize=(10,6))
plt.xticks(rotation=60)
dfdiff = dfdiff.drop("date",axis = 1).astype("float32")

#用某日前8天窗口数据作为输入预测该日数据
WINDOW_SIZE = 8

def batch_dataset(dataset):
    dataset_batched = dataset.batch(WINDOW_SIZE,drop_remainder=True)
    return dataset_batched

ds_data = tf.data.Dataset.from_tensor_slices(tf.constant(dfdiff.values,dtype = tf.float32)) \
   .window(WINDOW_SIZE,shift=1).flat_map(batch_dataset)

ds_label = tf.data.Dataset.from_tensor_slices(
    tf.constant(dfdiff.values[WINDOW_SIZE:],dtype = tf.float32))

#数据较小，可以将全部训练数据放入到一个batch中，提升性能
ds_train = tf.data.Dataset.zip((ds_data,ds_label)).batch(38).cache()

定义模型：这里我们用函数式模型

#考虑到新增确诊，新增治愈，新增死亡人数数据不可能小于0，设计如下结构
class Block(layers.Layer):
    def __init__(self, **kwargs):
        super(Block, self).__init__(**kwargs)
    
    def call(self, x_input,x):
        x_out = tf.maximum((1+x)*x_input[:,-1,:],0.0)
        return x_out
    
    def get_config(self):  
        config = super(Block, self).get_config()
        return config
tf.keras.backend.clear_session()
x_input = layers.Input(shape = (None,3),dtype = tf.float32)
x = layers.LSTM(3,return_sequences = True,input_shape=(None,3))(x_input)
x = layers.LSTM(3,return_sequences = True,input_shape=(None,3))(x)
x = layers.LSTM(3,return_sequences = True,input_shape=(None,3))(x)
x = layers.LSTM(3,input_shape=(None,3))(x)
x = layers.Dense(3)(x)

#考虑到新增确诊，新增治愈，新增死亡人数数据不可能小于0，设计如下结构
#x = tf.maximum((1+x)*x_input[:,-1,:],0.0)
x = Block()(x_input,x)
model = models.Model(inputs = [x_input],outputs = [x])
model.summary()

'''
Model: "model"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         [(None, None, 3)]         0         
_________________________________________________________________
lstm (LSTM)                  (None, None, 3)           84        
_________________________________________________________________
lstm_1 (LSTM)                (None, None, 3)           84        
_________________________________________________________________
lstm_2 (LSTM)                (None, None, 3)           84        
_________________________________________________________________
lstm_3 (LSTM)                (None, 3)                 84        
_________________________________________________________________
dense (Dense)                (None, 3)                 12        
_________________________________________________________________
block (Block)                (None, 3)                 0         
=================================================================
Total params: 348
Trainable params: 348
Non-trainable params: 0
_________________________________________________________________
'''

训练模型

#自定义损失函数，考虑平方差和预测目标的比值
class MSPE(losses.Loss):
    def call(self,y_true,y_pred):
        err_percent = (y_true - y_pred)**2/(tf.maximum(y_true**2,1e-7))
        mean_err_percent = tf.reduce_mean(err_percent)
        return mean_err_percent
    
    def get_config(self):
        config = super(MSPE, self).get_config()
        return config
import os
import datetime

optimizer = tf.keras.optimizers.Adam(learning_rate=0.01)
model.compile(optimizer=optimizer,loss=MSPE(name = "MSPE"))

stamp = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
logdir = os.path.join('data', 'autograph', stamp)

## 在 Python3 下建议使用 pathlib 修正各操作系统的路径
# from pathlib import Path
# stamp = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
# logdir = str(Path('./data/autograph/' + stamp))

tb_callback = tf.keras.callbacks.TensorBoard(logdir, histogram_freq=1)
#如果loss在100个epoch后没有提升，学习率减半。
lr_callback = tf.keras.callbacks.ReduceLROnPlateau(monitor="loss",factor = 0.5, patience = 100)
#当loss在200个epoch后没有提升，则提前终止训练。
stop_callback = tf.keras.callbacks.EarlyStopping(monitor = "loss", patience= 200)
callbacks_list = [tb_callback,lr_callback,stop_callback]

history = model.fit(ds_train,epochs=500,callbacks = callbacks_list)

'''
只展示最后5个
Epoch 495/500
1/1 [==============================] - 0s 50ms/step - loss: 0.0858
Epoch 496/500
1/1 [==============================] - 0s 69ms/step - loss: 0.0859
Epoch 497/500
1/1 [==============================] - 0s 63ms/step - loss: 0.0857
Epoch 498/500
1/1 [==============================] - 0s 56ms/step - loss: 0.0858
Epoch 499/500
1/1 [==============================] - 0s 54ms/step - loss: 0.0857
Epoch 500/500
1/1 [==============================] - 0s 57ms/step - loss: 0.0858
'''

评估模型

%matplotlib inline
%config InlineBackend.figure_format = 'svg'

import matplotlib.pyplot as plt

def plot_metric(history, metric):
    train_metrics = history.history[metric]
    epochs = range(1, len(train_metrics) + 1)
    plt.plot(epochs, train_metrics, 'bo--')
    plt.title('Training '+ metric)
    plt.xlabel("Epochs")
    plt.ylabel(metric)
    plt.legend(["train_"+metric])
    plt.show()
plot_metric(history,"loss")

使用模型

#使用dfresult记录现有数据以及此后预测的疫情数据
dfresult = dfdiff[["confirmed_num","cured_num","dead_num"]].copy()
dfresult.tail()

#预测此后100天的新增走势,将其结果添加到dfresult中
for i in range(100):
    arr_predict = model.predict(tf.constant(tf.expand_dims(dfresult.values[-38:,:],axis = 0)))

    dfpredict = pd.DataFrame(tf.cast(tf.floor(arr_predict),tf.float32).numpy(),
                columns = dfresult.columns)
    dfresult = dfresult.append(dfpredict,ignore_index=True)

dfresult.query("confirmed_num==0").head()

# 第55天开始新增确诊降为0，第45天对应3月10日，也就是10天后，即预计3月20日新增确诊降为0
# 注：该预测偏乐观


dfresult.query("cured_num==0").head()

# 第164天开始新增治愈降为0，第45天对应3月10日，也就是大概4个月后，即7月10日左右全部治愈。
# 注: 该预测偏悲观，并且存在问题，如果将每天新增治愈人数加起来，将超过累计确诊人数。

保存模型

model.save('./data/tf_model_savedmodel', save_format="tf")